Code to reproduce results in the paper

Mudrakarta, Pramod Kaushik, Ankur Taly, Mukund Sundararajan, and Kedar Dhamdhere. "Did the Model Understand the Question?." ACL 2018.

@article{mudrakarta2018did,
  title={Did the Model Understand the Question?},
  author={Mudrakarta, Pramod Kaushik and Taly, Ankur and Sundararajan, Mukund and Dhamdhere, Kedar},
  journal={arXiv preprint arXiv:1805.05492},
  year={2018}
}

Clone the repository using

git clone https://github.com/pramodkaushik/acl18_results.git --recursive

Attacks on Neural Programmer are present in the folder np_analysis, and those on visual question answering in visual_qa_analysis. Code for computing attributions via Integrated Gradients and to reproduce experiments are in Jupyter notebooks in both these directories.

Pramod Kaushik Mudrakarta

[email protected]